© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12984
    Prev
    Next
    INDEX
    Explanations

    Ad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     व्यव
    -0.08
    રી
    -0.08
    ्क
    -0.08
    ર્ત
    -0.07
    બ
    -0.07
    ્ક
    -0.07
     Guillaume
    -0.07
     Viva
    -0.07
    ージ
    -0.07
    .W
    -0.07
    POSITIVE LOGITS
     pays
    0.09
     Beginn
    0.08
     nami
    0.08
     consectetur
    0.08
    OC
    0.07
     gastos
    0.07
     proxim
    0.07
     réalis
    0.07
     Bennett
    0.07
    ища
    0.07
    Activations Density 0.002%

    No Known Activations